INDEX

Explanations

words related to negative or harmful consequences

oai_token-act-pair · gpt-3.5-turbo

variations of the root word "unwind" and related terms that imply relaxation or release from tension

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ioxide

-0.72

 mindfulness

-0.63

 Banks

-0.61

undy

-0.61

è£ħ

-0.60

 dens

-0.60

tein

-0.60

 stink

-0.58

 Anniversary

-0.57

uddin

-0.57

POSITIVE LOGITS

ledged

0.97

âĶĢâĶĢâĶĢâĶĢ

0.82

iable

0.82

edIn

0.78

ministic

0.74

visible

0.74

ables

0.70

itable

0.70

yet

0.70

ractive

0.70

Activations Density 0.091%

words related to negative or harmful consequences

variations of the root word "unwind" and related terms that imply relaxation or release from tension

No Comments

No Known Activations